Annotations#

Hide imports
%load_ext autoreload
%autoreload 2

import os

import dimcat as dc
import ms3
import plotly.express as px
from dimcat import groupers, plotting

import utils
Hide source
RESULTS_PATH = os.path.abspath(os.path.join(utils.OUTPUT_FOLDER, "overview"))
os.makedirs(RESULTS_PATH, exist_ok=True)


def make_output_path(
    filename: str,
    extension=None,
    path=RESULTS_PATH,
) -> str:
    return utils.make_output_path(filename=filename, extension=extension, path=path)


def save_figure_as(
    fig, filename, formats=("png", "pdf"), directory=RESULTS_PATH, **kwargs
):
    if formats is not None:
        for fmt in formats:
            plotting.write_image(fig, filename, directory, format=fmt, **kwargs)
    else:
        plotting.write_image(fig, filename, directory, **kwargs)

Loading data

Hide source
D = utils.get_dataset("bartok_bagatelles", corpus_release="v2.4")
package = D.inputs.get_package()
package_info = package._package.custom
git_tag = package_info.get("git_tag")
utils.print_heading("Data and software versions")
print("Béla Bartók – 14 Bagatelles, Op. 6 version v2.4")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D
Data and software versions
--------------------------

Béla Bartók – 14 Bagatelles, Op. 6 version v2.4
Datapackage 'bartok_bagatelles' @ v2.4
dimcat version 3.4.0
Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'bartok_bagatelles': ["'bartok_bagatelles.measures' (MuseScoreFacetName.MuseScoreMeasures)",
                                               "'bartok_bagatelles.notes' (MuseScoreFacetName.MuseScoreNotes)",
                                               "'bartok_bagatelles.expanded' (MuseScoreFacetName.MuseScoreHarmonies)",
                                               "'bartok_bagatelles.chords' (MuseScoreFacetName.MuseScoreChords)",
                                               "'bartok_bagatelles.metadata' (FeatureName.Metadata)"]}},
 'outputs': {'basepath': None, 'packages': {}},
 'pipeline': []}
filtered_D = D.apply_step("HasHarmonyLabelsFilter")
all_metadata = filtered_D.get_metadata()
assert len(all_metadata) > 0, "No pieces selected for analysis."
chronological_corpus_names = all_metadata.get_corpus_names()

DCML harmony labels#

Hide source
all_annotations = filtered_D.get_feature("DcmlAnnotations")
is_annotated_mask = all_metadata.label_count > 0
is_annotated_index = all_metadata.index[is_annotated_mask]
annotated_notes = filtered_D.get_feature("notes").subselect(is_annotated_index)
print(f"The annotated pieces have {len(annotated_notes)} notes.")
The annotated pieces have 9910 notes.
all_chords = filtered_D.get_feature("harmonylabels")
print(
    f"{len(all_annotations)} annotations, of which {len(all_chords)} are harmony labels."
)
1191 annotations, of which 1175 are harmony labels.

Harmony labels#

Unigrams#

For computing unigram statistics, the tokens need to be grouped by their occurrence within a major or a minor key because this changes their meaning. To that aim, the annotated corpus needs to be sliced into contiguous localkey segments which are then grouped into a major (is_minor=False) and a minor group.

root_durations = (
    all_chords[all_chords.root.between(-5, 6)]
    .groupby(["root", "chord_type"])
    .duration_qb.sum()
)
# sort by stacked bar length:
# root_durations = root_durations.sort_values(key=lambda S: S.index.get_level_values(0).map(S.groupby(level=0).sum()),
# ascending=False)
bar_data = root_durations.reset_index()
bar_data.root = bar_data.root.map(ms3.fifths2iv)
fig = px.bar(
    bar_data,
    x="root",
    y="duration_qb",
    color="chord_type",
    title="Distribution of chord types over chord roots",
    labels=dict(
        root="Chord root expressed as interval above the local (or secondary) tonic",
        duration_qb="duration in quarter notes",
        chord_type="chord type",
    ),
)
fig.update_layout(**utils.STD_LAYOUT)
save_figure_as(fig, "chord_type_distribution_over_scale_degrees_absolute_stacked_bars")
fig.show()
relative_roots = all_chords[
    ["numeral", "duration_qb", "relativeroot", "localkey_is_minor", "chord_type"]
].copy()
relative_roots["relativeroot_resolved"] = ms3.transform(
    relative_roots, ms3.resolve_relative_keys, ["relativeroot", "localkey_is_minor"]
)
has_rel = relative_roots.relativeroot_resolved.notna()
relative_roots.loc[has_rel, "localkey_is_minor"] = relative_roots.loc[
    has_rel, "relativeroot_resolved"
].str.islower()
relative_roots["root"] = ms3.transform(
    relative_roots, ms3.roman_numeral2fifths, ["numeral", "localkey_is_minor"]
)
chord_type_frequency = all_chords.chord_type.value_counts()
replace_rare = ms3.map_dict(
    {t: "other" for t in chord_type_frequency[chord_type_frequency < 500].index}
)
relative_roots["type_reduced"] = relative_roots.chord_type.map(replace_rare)
# is_special = relative_roots.chord_type.isin(('It', 'Ger', 'Fr'))
# relative_roots.loc[is_special, 'root'] = -4
root_durations = (
    relative_roots.groupby(["root", "type_reduced"])
    .duration_qb.sum()
    .sort_values(ascending=False)
)
bar_data = root_durations.reset_index()
bar_data.root = bar_data.root.map(ms3.fifths2iv)
root_order = (
    bar_data.groupby("root")
    .duration_qb.sum()
    .sort_values(ascending=False)
    .index.to_list()
)
fig = px.bar(
    bar_data,
    x="root",
    y="duration_qb",
    color="type_reduced",
    barmode="group",
    log_y=True,
    color_discrete_map=utils.TYPE_COLORS,
    category_orders=dict(
        root=root_order,
        type_reduced=relative_roots.type_reduced.value_counts().index.to_list(),
    ),
    labels=dict(
        root="intervallic difference between chord root to the local or secondary tonic",
        duration_qb="duration in quarter notes",
        type_reduced="chord type",
    ),
    width=1000,
    height=400,
)
fig.update_layout(
    **utils.STD_LAYOUT,
    legend=dict(
        orientation="h",
        xanchor="right",
        x=1,
        y=1,
    ),
)
save_figure_as(fig, "chord_type_distribution_over_scale_degrees_absolute_grouped_bars")
fig.show()
print(
    f"Reduced to {len(set(bar_data.iloc[:,:2].itertuples(index=False, name=None)))} types. "
    f"Paper cites the sum of types in major and types in minor (see below), treating them as distinct."
)
Reduced to 20 types. Paper cites the sum of types in major and types in minor (see below), treating them as distinct.
dim_or_aug = bar_data[
    bar_data.root.str.startswith("a") | bar_data.root.str.startswith("d")
].duration_qb.sum()
complete = bar_data.duration_qb.sum()
print(
    f"On diminished or augmented scale degrees: {dim_or_aug} / {complete} = {dim_or_aug / complete}"
)
On diminished or augmented scale degrees: 187.75 / 2292.4375 = 0.08189972463807628
chords_by_mode = groupers.ModeGrouper().process(all_chords)
chords_by_mode.format = "scale_degree"

Whole dataset#

unigram_proportions = chords_by_mode.get_default_analysis()
unigram_proportions.make_ranking_table()
mode major minor
chord_and_mode scale_degrees duration_qb proportion proportion_% chord_and_mode scale_degrees duration_qb proportion proportion_%
rank
1 IM7, major (1, 3, 5, 7) 44.00 0.028758 2.88 % i7, minor (1, 3, 5, 7) 99.0 0.129847 12.98 %
2 V, major (5, 7, 2) 33.00 0.021569 2.16 % i, minor (1, 3, 5) 21.5 0.028199 2.82 %
3 I, major (1, 3, 5) 26.00 0.016993 1.7 % VIM7, minor (6, 1, 3, 5) 18.0 0.023608 2.36 %
4 I(b109), major (1, 3, 5) 25.00 0.016340 1.63 % vii%7(+9)/bVI, minor (b5, b7, bb2, b4) 18.0 0.023608 2.36 %
5 V64(b13b9#4), major (#1, 5, 7) 24.00 0.015686 1.57 % V64(+6), minor (2, 5, #7) 15.0 0.019674 1.97 %
... ... ... ... ... ... ... ... ... ... ...
526 bII(#10b9), major (b2, 4, b6) 0.25 0.000163 0.02 % NaN NaN NaN NaN NaN
527 bVI(#10b9), major (b6, 1, b3) 0.25 0.000163 0.02 % NaN NaN NaN NaN NaN
528 bV6(11b9), major (b7, b2, b5) 0.25 0.000163 0.02 % NaN NaN NaN NaN NaN
529 V7(9)/bV, major (b2, 4, b6, b1) 0.25 0.000163 0.02 % NaN NaN NaN NaN NaN
530 III(11b9), major (3, #5, 7) 0.25 0.000163 0.02 % NaN NaN NaN NaN NaN

530 rows × 10 columns

chords_by_mode.apply_step("Counter")
count
mode corpus piece chord_and_mode scale_degrees
major bartok_bagatelles op06n01 io65, major (b3, b5, bb7, 1) 2
V(9), major (5, 7, 2) 2
I, major (1, 3, 5) 2
I(9), major (1, 3, 5) 1
iv6, major (b6, 1, 4) 1
... ... ... ... ... ...
minor bartok_bagatelles op06n13 iM7(#11), minor (1, 3, 5, #7) 1
iM7(13#10), minor (1, 3, 5, #7) 1
#iv(+b9), minor (#4, #6, #1) 1
#iv(#13), minor (#4, #6, #1) 1
op06n14 iM7, minor (1, 3, 5, #7) 1

805 rows × 1 columns

chords_by_mode.format = "scale_degree"
chords_by_mode.get_default_analysis().make_ranking_table()
mode major minor
chord_and_mode scale_degrees duration_qb proportion proportion_% chord_and_mode scale_degrees duration_qb proportion proportion_%
rank
1 IM7, major (1, 3, 5, 7) 44.00 0.028758 2.88 % i7, minor (1, 3, 5, 7) 99.0 0.129847 12.98 %
2 V, major (5, 7, 2) 33.00 0.021569 2.16 % i, minor (1, 3, 5) 21.5 0.028199 2.82 %
3 I, major (1, 3, 5) 26.00 0.016993 1.7 % VIM7, minor (6, 1, 3, 5) 18.0 0.023608 2.36 %
4 I(b109), major (1, 3, 5) 25.00 0.016340 1.63 % vii%7(+9)/bVI, minor (b5, b7, bb2, b4) 18.0 0.023608 2.36 %
5 V64(b13b9#4), major (#1, 5, 7) 24.00 0.015686 1.57 % V64(+6), minor (2, 5, #7) 15.0 0.019674 1.97 %
... ... ... ... ... ... ... ... ... ... ...
526 bII(#10b9), major (b2, 4, b6) 0.25 0.000163 0.02 % NaN NaN NaN NaN NaN
527 bVI(#10b9), major (b6, 1, b3) 0.25 0.000163 0.02 % NaN NaN NaN NaN NaN
528 bV6(11b9), major (b7, b2, b5) 0.25 0.000163 0.02 % NaN NaN NaN NaN NaN
529 V7(9)/bV, major (b2, 4, b6, b1) 0.25 0.000163 0.02 % NaN NaN NaN NaN NaN
530 III(11b9), major (3, #5, 7) 0.25 0.000163 0.02 % NaN NaN NaN NaN NaN

530 rows × 10 columns

unigram_proportions.plot_grouped()